diff options
author | Vlastimil Babka <vbabka@suse.cz> | 2017-07-07 00:39:59 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-07 01:24:34 +0200 |
commit | 45816682b2cd6771cf63cb7dc7dbebdd827a0132 (patch) | |
tree | 09c1c5ee154b91bfe85780b4e6d771fd305c36e2 /mm/mempolicy.c | |
parent | mm, page_alloc: fix more premature OOM due to race with cpuset update (diff) | |
download | linux-45816682b2cd6771cf63cb7dc7dbebdd827a0132.tar.xz linux-45816682b2cd6771cf63cb7dc7dbebdd827a0132.zip |
mm, mempolicy: stop adjusting current->il_next in mpol_rebind_nodemask()
The task->il_next variable stores the next allocation node id for task's
MPOL_INTERLEAVE policy. mpol_rebind_nodemask() updates interleave and
bind mempolicies due to changing cpuset mems. Currently it also tries
to make sure that current->il_next is valid within the updated nodemask.
This is bogus, because 1) we are updating potentially any task's
mempolicy, not just current, and 2) we might be updating a per-vma
mempolicy, not task one.
The interleave_nodes() function that uses il_next can cope fine with the
value not being within the currently allowed nodes, so this hasn't
manifested as an actual issue.
We can remove the need for updating il_next completely by changing it to
il_prev and store the node id of the previous interleave allocation
instead of the next id. Then interleave_nodes() can calculate the next
id using the current nodemask and also store it as il_prev, except when
querying the next node via do_get_mempolicy().
Link: http://lkml.kernel.org/r/20170517081140.30654-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Christoph Lameter <cl@linux.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r-- | mm/mempolicy.c | 22 |
1 files changed, 7 insertions, 15 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 37d0b334bfe9..d77177c7283b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -349,12 +349,6 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes, pol->v.nodes = tmp; else BUG(); - - if (!node_isset(current->il_next, tmp)) { - current->il_next = next_node_in(current->il_next, tmp); - if (current->il_next >= MAX_NUMNODES) - current->il_next = numa_node_id(); - } } static void mpol_rebind_preferred(struct mempolicy *pol, @@ -812,9 +806,8 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, } old = current->mempolicy; current->mempolicy = new; - if (new && new->mode == MPOL_INTERLEAVE && - nodes_weight(new->v.nodes)) - current->il_next = first_node(new->v.nodes); + if (new && new->mode == MPOL_INTERLEAVE) + current->il_prev = MAX_NUMNODES-1; task_unlock(current); mpol_put(old); ret = 0; @@ -916,7 +909,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { - *policy = current->il_next; + *policy = next_node_in(current->il_prev, pol->v.nodes); } else { err = -EINVAL; goto out; @@ -1697,14 +1690,13 @@ static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy, /* Do dynamic interleaving for a process */ static unsigned interleave_nodes(struct mempolicy *policy) { - unsigned nid, next; + unsigned next; struct task_struct *me = current; - nid = me->il_next; - next = next_node_in(nid, policy->v.nodes); + next = next_node_in(me->il_prev, policy->v.nodes); if (next < MAX_NUMNODES) - me->il_next = next; - return nid; + me->il_prev = next; + return next; } /* |